Atomic blocks allow programmers to delimit sections of code as 'atomic', leaving the language's implementation to enforce atomicity. Existing work has shown how to implement atomic blocks over word-based transactional memory that provides scalable multi-processor performance without requiring changes to the basic structure of objects in the heap. However, these implementations perform poorly because they interpose on all accesses to shared memory in the atomic block, redirecting updates to a thread-private log which must be searched by reads in the block and later reconciled with the heap when leaving the block.This paper takes a four-pronged approach to improving performance: (1) we introduce a new 'direct access' implementation that avoids searching thread-private logs, (2) we develop compiler optimizations to reduce the amount of logging (e.g. when a thread accesses the same data repeatedly in an atomic block), (3) we use runtime filtering to detect duplicate log entries that are missed statically, and (4) we present a series of GC-time techniques to compact the logs generated by long-running atomic blocks.Our implementation supports short-running scalable concurrent benchmarks with less than 50\% overhead over a non-thread-safe baseline. We support long atomic blocks containing millions of shared memory accesses with a 2.5-4.5x slowdown.

This paper presents the initial results of a project to determine if the techniques of proof-carrying code and certifying compilers can be applied to programming languages of realistic size and complexity. The experiment shows that: (1) it is possible to implement a certifying native-code compiler for a large subset of the Java programming language; (2) the compiler is freely able to apply many standard local and global optimizations; and (3) the PCC binaries it produces are of reasonable size and can be rapidly checked for type safety by a small proof-checker. This paper also presents further evidence that PCC provides several advantages for compiler development. In particular, generating proofs of the target code helps to identify compiler bugs, many of which would have been dicult to discover by testing.